Health

Cutting through the fog of long COVID

AI and medical records illustration.
5 min read

Researchers say new AI tool sharpens diagnostic process, may help identify more people needing care

While earlier diagnostic studies have suggested that 7 percent of the population suffers from long COVID, a new AI tool developed by  Mass General Brigham revealed a much higher 22.8 percent, according to the study. 

The AI-based tool can sift through electronic health records to help clinicians identify cases of long COVID. The often-mysterious condition can encompass a litany of enduring symptoms, including fatigue, chronic cough, and brain fog after infection from SARS-CoV-2. 

The algorithm used was developed by drawing de-identified patient data from the clinical records of nearly 300,000 patients across 14 hospitals and 20 community health centers in the Mass General Brigham system. The results, published in the journal Med, could identify more people who should be receiving care for this potentially debilitating condition.

“Our AI tool could turn a foggy diagnostic process into something sharp and focused, giving clinicians the power to make sense of a challenging condition,” said senior author Hossein Estiri, head of AI Research at the Center for AI and Biomedical Informatics of the Learning Healthcare System (CAIBILS) at MGB and an associate professor of medicine at Harvard Medical School. “With this work, we may finally be able to see long COVID for what it truly is — and more importantly, how to treat it.”

“With this work, we may finally be able to see long COVID for what it truly is — and more importantly, how to treat it.”

Hossein Estiri

For the purposes of their study, Estiri and colleagues defined long COVID as a diagnosis of exclusion that is also infection-associated. That means the diagnosis could not be explained in the patient’s unique medical record but was associated with a COVID infection. In addition, the diagnosis needed to have persisted for two months or longer in a 12-month follow up window. 

The novel method developed by Estiri and colleagues, called “precision phenotyping,” sifts through individual records to identify symptoms and conditions linked to COVID-19 to track symptoms over time in order to differentiate them from other illnesses. For example, the algorithm can detect if shortness of breath results from pre-existing conditions like heart failure or asthma rather than long COVID. Only when every other possibility was exhausted would the tool flag the patient as having long COVID. 

“Physicians are often faced with having to wade through a tangled web of symptoms and medical histories, unsure of which threads to pull, while balancing busy caseloads. Having a tool powered by AI that can methodically do it for them could be a game-changer,” said Alaleh Azhir, co-lead author and an internal medicine resident at Brigham and Women’s Hospital, a founding member of the Mass General Brigham healthcare system.

The new tool’s patient-centered diagnoses may also help alleviate biases built into current diagnostics for long COVID, said researchers, who noted diagnoses with the official ICD-10 diagnostic code for long COVID trend toward those with easier access to healthcare.

The researchers said their tool is about 3 percent more accurate than the data ICD-10 codes capture, while being less biased. Specifically, their study demonstrated that the individuals they identified as having long COVID mirror the broader demographic makeup of Massachusetts, unlike long COVID algorithms that rely on a single diagnostic code or individual clinical encounters, skewing results toward certain populations such as those with more access to care.

“This broader scope ensures that marginalized communities, often sidelined in clinical studies, are no longer invisible,” said Estiri.

Limitations of the study and AI tool include that health record data the algorithm uses to account for long COVID symptoms may be less complete than the data physicians capture in post-visit clinical notes. Another limitation was the algorithm did not capture possible worsening of a prior condition that may have been a long COVID symptom. For example, if a patient had COPD that worsened before they developed COVID-19, the algorithm might have removed the episodes even if they were long COVID indicators. Declines in COVID-19 testing in recent years also makes it difficult to identify when a patient may have first gotten COVID-19.

The study was limited to patients in Massachusetts.

Future studies may explore the algorithm in cohorts of patients with specific conditions, like COPD or diabetes. The researchers also plan to release this algorithm publicly on open access so physicians and healthcare systems globally can use it in their patient populations. 

In addition to opening the door to better clinical care, this work may lay the foundation for future research into the genetic and biochemical factors behind long COVID’s various subtypes. “Questions about the true burden of long COVID — questions that have thus far remained elusive — now seem more within reach,” said Estiri.

Support was given by the National Institutes of Health, National Institute of Allergy and Infectious Diseases (NIAID) R01AI165535, National Heart, Lung, and Blood Institute (NHLBI) OT2HL161847, and National Center for Advancing Translational Sciences (NCATS) UL1 TR003167, UL1 TR001881, and U24TR004111. J. Hügel’s work was partially funded by a fellowship within the IFI program of the German Academic Exchange Service (DAAD) and by the Federal Ministry of Education and Research (BMBF) as well by the German Research Foundation (426671079).